Backend-Focused Multi-Model Workflow
SkillAI & modelsAdvanced: Backend-focused multi-model workflow (Research → Ideation → Plan → Execute → Optimize → Review), Codex-led.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Backend-Focused Multi-Model Workflow skill
What this skill tells your AI
The instructions your AI receives, as published by luohaothu/everything-codex in skills/multi-backend/SKILL.md and read by ahel’s review.
Advanced skill — Backend-focused development with Codex-led multi-model collaboration.
Usage
/multi-backend <backend task description>
Applicability
API design, algorithm implementation, database optimization, business logic, server-side processing.
Phases
Phase 1: Research
Understand requirements, retrieve existing APIs, data models, service architecture.
Phase 2: Ideation (Codex-Led)
- Call Codex backend for technical feasibility analysis
- Output: recommended solutions (at least 2), risk assessment
- Wait for user selection
Phase 3: Planning (Codex-Led)
- Call Codex for architecture design
- Output: file structure, function/class design, dependencies
- Save plan, wait for user approval
Phase 4: Implementation
Follow approved plan, ensure error handling, security, performance.
Phase 5: Optimization (Codex-Led)
- Call Codex for code review
- Focus: security, performance, error handling, API compliance
- Execute optimization after user confirmation
Phase 6: Quality Review
Check completion, run tests, report issues.
Key Rules
- Codex backend opinions are authoritative
- Other model backend opinions are for reference only
- External models have zero filesystem write access
- All code writes handled by the orchestrator
Signals
- GitHub stars
- 24
- Forks
- 5
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
multi-backend- Source
- github.com/luohaothu/everything-codex